About Apurvakhemani
What will be covered?
🔹 Session 1: Understand what data science really means, explore and prepare a real dataset for analysis.
🔹 Session 2: Build, evaluate, and improve predictive models while learning how these insights power business decisions. Plus, get clarity on the difference between Data Science and AI.
Session 1
🔹 Session 1: From Data to Prediction
1. What Exactly is Data Science?
• Data Science vs Analytics — explained simply
• Real-world use cases & industry workflows
2. Real-World Project Kick-off: Predictive Analysis in Action
🎯 Example Project: Customer Churn Prediction for a Telecom Company
Use historical customer data (e.g. contract type, service usage, support calls) to predict which users are at risk of leaving — and help the business take action before they do.
• Explore the dataset together (cleaned + raw)
• Understand the business impact of churn prediction
• Define your target variable and useful features
3. Data Exploration & Preparation
• Hands-on demo using Pandas
• Deal with missing values, outliers, and categorical data
• Prepare your dataset for modelling in Session 2
Session 2
1. Hands-On Predictive Modelling (using Session 1 Dataset)
• Train a Logistic Regression or Decision Tree model
• Evaluate model performance: accuracy, precision, recall, F1
• Improve your model: feature selection, balancing data, tuning
• Visualise model predictions
2. Real-World Impact: Why This Matters
• How businesses use predictive models to make decisions
(Example: How your model can help reduce churn)
• What happens after modelling: business actions, deployment
3. Industry-Ready Models – What You Should Know
• Common models used in the field:
✅ Logistic Regression
✅ Decision Trees & Random Forest
✅ XGBoost / Gradient Boosting
✅ Neural Networks (intro only)
• When to use what: model selection cheat sheet
4. Data Science vs AI – Know the Difference
• Where they overlap and where they don’t
• Career pathways and how to position yourself